# Effective Context and Fragment Feature Usage for Named Entity Recognition

## TL;DR

This paper introduces a novel NER approach that leverages FOFE encoding for context and fragment features, organizing them into groups for improved recognition performance using only tokenized text and word embeddings.

## Contribution

It presents a new method combining FOFE encoding with feature grouping and dedicated neural layers, enhancing NER accuracy without relying on complex features.

## Key findings

- Outperforms baseline models on NER tasks
- Competitive with state-of-the-art methods
- Effective use of context and fragment features

## Abstract

In this paper, we explore a new approach to named entity recognition (NER) with the goal of learning from context and fragment features more effectively, contributing to the improvement of overall recognition performance. We use the recent fixed-size ordinally forgetting encoding (FOFE) method to fully encode each sentence fragment and its left-right contexts into a fixed-size representation. Next, we organize the context and fragment features into groups, and feed each feature group to dedicated fully-connected layers. Finally, we merge each group's final dedicated layers and add a shared layer leading to a single output. The outcome of our experiments show that, given only tokenized text and trained word embeddings, our system outperforms our baseline models, and is competitive to the state-of-the-arts of various well-known NER tasks.